東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Tree-based methods for survival anal...

Zhu, Ruoqing.

Linked to FindBook

Google Book

Amazon

博客來

Tree-based methods for survival analysis and high-dimensional data.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Tree-based methods for survival analysis and high-dimensional data./
Author:	Zhu, Ruoqing.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2013,
Description:	122 p.
Notes:	Source: Dissertation Abstracts International, Volume: 75-04(E), Section: B.
Contained By:	Dissertation Abstracts International75-04B(E).
Subject:	Biostatistics. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3606793
ISBN:	9781303640407

Tree-based methods for survival analysis and high-dimensional data.
Zhu, Ruoqing.

Tree-based methods for survival analysis and high-dimensional data. - Ann Arbor : ProQuest Dissertations & Theses, 2013 - 122 p.

Source: Dissertation Abstracts International, Volume: 75-04(E), Section: B.

Thesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2013.

Machine learning techniques have garnered significant popularity due to their capacity to handle high dimensional data. Tree-based methods are among the most popular machine learning approaches. My dissertation aims on improving existing tree-based methods and developing statistical framework for understanding the proposed methods. It contains three topics: recursively imputed survival tree, reinforcement learning trees and reinforcement learning trees for right censored survival data. A central idea of my dissertation is focused on increasing the chance of using signaled variables as splitting rule during the tree construction while not losing the randomness/diversity, hence a more accurate model can be built. However, different methods achieve this by using different approaches. Recursively imputed survival tree recursively impute censored observations and refit the survival tree model. This approach allows better use of the censored observations during the tree construction, it also changes the dynamic of splitting rule selections during the tree construction so that signaled variables can be emphasized more in the refitted model. Reinforcement learning trees takes a direct approach to emphasize signaled variables in the tree construction. An embedded model is fitted at each internal node while searching for splitting rules. The variable with the largest variable importance measure is used as the splitting variable. A new theoretical framework is proposed to show consistency and convergence rate of this new approach. In the third topic, we further extend reinforcement learning trees to right censored survival data. Brier score is utilized to calculate the variable importance measures. We also show a desirable property of the proposed method that can help correct the bias of variable importance measures when correlated variables are present in the model.

ISBN: 9781303640407Subjects--Topical Terms:

1002712
Biostatistics.

Tree-based methods for survival analysis and high-dimensional data.
LDR:02848nmm a2200301 4500 001 2164213
005 20181030085012.5
008 190424s2013 ||||||||||||||||| ||eng d
020 $a 9781303640407
035 $a (MiAaPQ)AAI3606793
035 $a (MiAaPQ)unc:14056
035 $a AAI3606793
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhu, Ruoqing. $3 3352257
245 1 0 $a Tree-based methods for survival analysis and high-dimensional data.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2013
300 $a 122 p.
500 $a Source: Dissertation Abstracts International, Volume: 75-04(E), Section: B.
500 $a Adviser: Michael R. Kosorok.
502 $a Thesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2013.
520 $a Machine learning techniques have garnered significant popularity due to their capacity to handle high dimensional data. Tree-based methods are among the most popular machine learning approaches. My dissertation aims on improving existing tree-based methods and developing statistical framework for understanding the proposed methods. It contains three topics: recursively imputed survival tree, reinforcement learning trees and reinforcement learning trees for right censored survival data. A central idea of my dissertation is focused on increasing the chance of using signaled variables as splitting rule during the tree construction while not losing the randomness/diversity, hence a more accurate model can be built. However, different methods achieve this by using different approaches. Recursively imputed survival tree recursively impute censored observations and refit the survival tree model. This approach allows better use of the censored observations during the tree construction, it also changes the dynamic of splitting rule selections during the tree construction so that signaled variables can be emphasized more in the refitted model. Reinforcement learning trees takes a direct approach to emphasize signaled variables in the tree construction. An embedded model is fitted at each internal node while searching for splitting rules. The variable with the largest variable importance measure is used as the splitting variable. A new theoretical framework is proposed to show consistency and convergence rate of this new approach. In the third topic, we further extend reinforcement learning trees to right censored survival data. Brier score is utilized to calculate the variable importance measures. We also show a desirable property of the proposed method that can help correct the bias of variable importance measures when correlated variables are present in the model.
590 $a School code: 0153.
650 4 $a Biostatistics. $3 1002712
650 4 $a Statistics. $3 517247
690 $a 0308
690 $a 0463
710 2 $a The University of North Carolina at Chapel Hill. $b Biostatistics. $3 1023527
773 0 $t Dissertation Abstracts International $g 75-04B(E).
790 $a 0153
791 $a Ph.D.
792 $a 2013
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3606793